NORMA eResearch @NCI Library

Machine Learning Techniques for Prediction of Electricity Consumption in Buildings

Blaszczyk, Grzegorz (2022) Machine Learning Techniques for Prediction of Electricity Consumption in Buildings. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (207kB) | Preview


Energy use in buildings is responsible for 40% of total global energy consumption. With this in mind, it is imperative to focus on application of that energy to the most efficient use. This project is focusing on showing which machine learning algorithms are able to perform well to predict energy consumption. This project will utilise CRISP-DM methodology: from business understanding, through data exploration, preparation, and cleaning, to application of various machine learning techniques, and concludes with showing which ones are the best for the task. This work will demonstrate it on the example of one of the Kaggle competitions: ASHRAE - Great Energy Predictor III. Throughout this project a sytematic approach for a full cycle of data science project will be demonstrated, how to handle missing data in a relatively large dataset? Selection of good random samples, and application of machine learning algorithms to the samples, to conclude with comparison of results. The results will show that number of simple techniques achieved very similar results to the advanced ones however, they did that in time only a fraction of the techniques that were suggested in the literature.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electricity Supply
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 19 Jan 2023 13:18
Last Modified: 06 Mar 2023 15:58

Actions (login required)

View Item View Item